SimoneHill.FinalPaper.MarkovMelodyGenerator - Markov Melody Generator Simone Hill e-mail address <[email protected]> ABSTRACT In this paper an

SimoneHill.FinalPaper.MarkovMelodyGenerator - Markov Melody...

This preview shows page 1 - 2 out of 4 pages.

Markov Melody GeneratorSimone Hille-mail address <[email protected]>ABSTRACTIn this paper, an application called the Markov Melody Generator is designed for algorithmic music composition is demonstrated. The theory behind using human compositions to derive artificially generated melodies using Markov chains is discussed. A survey in which participants rate the generated melodies is taken and the results are evaluated. Further possibilities and ideas for expansion are discussed. Author KeywordsAlgorithmic composition, Markov Chains, Artificial Intelligence, Computational Creativity.INTRODUCTIONMarkov chains are employed in algorithmic music composition, particularly in software programs. Algorithmic composition is the technique of using algorithms to create music to be used by composers as creative inspiration for their music. Formal sets of rules have been used to compose music for centuries. The term “algorithmic composition” is usually reserved, however, for the use of formal procedures to make music without human intervention, either through the introduction of chance procedures or the use of computers. Interestingly, many composition algorithms employ models and data that have no musical relevance. Even arbitrary data is fair game for musical interpretation. The success or failure of these procedures as sources of "good" music largely depends on the mapping employed by the composer to translate the non-musical information into a musical data stream.PROJECT DESCRIPTIONThe most common way to create compositions through mathematics is stochastic processes. In stochastic models a piece of music is composed as a result of non-deterministic methods. The compositional process is only partially controlled by the composer by weighting the possibilities of random events. Prominent examples of stochastic algorithms are Markov chains, hence the title "Markov Melody Generator".Applying Markov Chains to MusicIn a first-order chain, the states of the system become note or pitch values, and a probability vector for each note is constructed, completing a transition probability matrix.Example:NoteAC# EA0.10.60.3C#0.250.050.7E0.70.30To calculate the probability transitional matrix, we can use anything, including arbitrary data. However, for the purposes of this project, it may be more interesting to model the melody generator after other melodies. For example, if the melody pitches from Beethoven's “Ode to Joy” were written out as:EEFG GFED CCDE EDD EEFG GFED CCDE DCCDDEC DEFEC DEFED CDG EEFG GFED CCDE DCC Starting at the beginning, a probability table can be created by listing the frequencies of each successive note in the melody.E moves to: E E F F F F F D D D D D D D E E C C C moves to: C C C C C D D D D D D D F moves to: G G G E E E E E E D moves to: G C C C C C C E E E E E E E D D G moves to: E G F F FSo, for example, the note G moves to E one out of five times, to the note G one out of five times, and to the note F three out of five times. And so on, the rest of the transition

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture